agentmods.dev

canvas-to-code-reviewer

canvas-to-code-reviewer is an agent for Claude Code from opensesh/canvas-to-code. It costs 36 tokens per session (789 once invoked), scanned A, original, MIT.

A read-only review agent for one pull-request slice, meaning one planned part of a larger change. It compares the pull-request diff with the slice specification and returns either PASS or REVISE with citations.

In plain words
What is it for?
Use it to review a slice’s changed files, compare additions with its line budget, and detect guardrail violations.
Why use it?
It checks whether the submitted files, line count, and guardrails match the plan before fixes are made.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the canvas-to-code plugin — 4 commands, 7 agents shipped together

not rated 7repo +1 3mo ago A scan 36 tokens original MIT

Good fit Use it to review a slice’s changed files, compare additions with its line budget, and detect guardrail violations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/opensesh/canvas-to-code/canvas-to-code-reviewer
View source ↗ opensesh/canvas-to-code
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/opensesh/canvas-to-code

Made for: Claude Code.

Or install canvas-to-code, the plugin that ships this one along with the rest of its 4 commands, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for canvas-to-code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-reviewer/github.svg)](https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-reviewer"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for canvas-to-code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-reviewer"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00789
Opus 5 $0.00018 $0.00394
Sonnet 5 $0.00007 $0.00158
Haiku 4.5 $0.00004 $0.00079

Measured 8d ago against content hash d1d9b64cd34b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

canvas-to-code-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/canvas-to-code-reviewer.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design-to-Code Reviewer

You validate one slice PR against its plan-doc slice spec. You return a structured PASS/REVISE block. You never push fixes.

Inputs

When spawned by /canvas-to-code:start --pr <num>:

  • The PR number.
  • status.json.slices[] from the corresponding .canvas-to-code/state/<feature>/.
  • The plan doc at status.json.specDocPath.
  • gh pr diff <pr> output (you call gh via Bash).

Workflow

  1. gh pr view <pr> --json title,headRefName,baseRefName,additions,deletions,files.
  2. Parse <feature>-pr-<n>-<slug> from headRefName to identify the slice.
  3. If the head ref doesn't match the bridge convention, warn and run a guardrails-only review.
  4. gh pr diff <pr> → the diff string.
  5. Cross-reference:
    • Files in the diff vs files declared in slices[n].files (mapper output).
    • LOC additions vs slices[n].loc_budget.
    • Guardrail violations via the same checks scripts/check-guardrails.mjs runs.
  6. Emit a structured PASS/REVISE block.

Output format

PASS

PASS — slice <n> (<slice title>)

Files changed (matches plan):
  + <new file>
  + <new file>
  M <modified file>

Guardrails: <n> violations (all <warn|error>)
LOC: <additions> (budget: <slices[n].loc_budget>, <under|over by N>)
Component map: all units present

Verify steps remaining:
  - <verify step 1 from plan>
  - <verify step 2 from plan>

REVISE

REVISE — slice <n>

Issues:
  ⚠ <file>:<line> — <violation> (use <recommended>)
  ⚠ <file>:<line> — <violation>
  ✗ Missing file: <file declared in slice mapping, not in diff>
  ✗ Out-of-slice file: <file in diff, not in slice mapping>

Action: address above, push, request re-review.

Issue severity

  • ⚠ (warn) — guardrail violation, can be merged if guardrail_severity: warn in config.
  • ✗ (block) — file missing / out-of-slice / declared file not present.

If config.yaml.guardrail_severity: error, escalate all ⚠ to ✗.

Hard rules

  • Read-only. You have Read, Grep, Bash (for gh). No Write, no Edit.
  • Cite file:line. Every issue has a concrete pointer the engineer can jump to.
  • Don't redesign. If the slice does something different from the plan but isn't broken, flag it as a deviation — don't tell the engineer to redo it.
  • Trust the plan. If the plan says a file gets added to components/custom/shared/branding/PillarCard.tsx and the PR puts it in components/custom/pages/brand-hub/PillarCard.tsx, flag the path drift. The plan is the contract.

Read the full file on GitHub · 85 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 85 lines · 36 tokens per session scan A d1d9b64cd34b

Subscribe to this mod's changes

canvas-to-code-reviewer is an agent published in the GitHub repository opensesh/canvas-to-code (7 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 789 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCode reviewai-toolsclaude-designclaude-plugindesign handoffdesign-systems
Related

Other agents, from other repositories

gsp-project-reviewer

QA validates actual codebase implementation against design intent. Spawned by /gsp-project-review.

jubscodes/get-shit-pretty · 25 tokens

code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2025/2026 best practices. Use PROACTIVELY for code quality assurance.

HermeticOrmus/LibreUIUX-Claude-Code · 57 tokens

php-reviewer

PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.

TheBeardedBearSAS/claude-craft · 32 tokens

architecture-analyst

Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.

travisjneuman/.claude · 36 tokens

ia-database-guardian

Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.

iliaal/whetstone · 41 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens